RTX 3090 本地跑 Qwen、GLM 与 V4.1 Flash 的现状

AJ @ItsmeAjayKV原推发布于 2026.10.22

在 X 上打开原推

The models i'm running now on my RTX 3090 was an impossible dream just few months ago. When i bought my used 3090, back in June, all i ever wanted was to run Qwen3.6-27B ! Now i'm running - Qwen3.8-Flash-Next - GLM-5.3-Flash - DeepSeek-v4.1-Flash-1017 (barely for now, will get better👀) Models are getting better ! Inference engines getting better ! All of this is giving my 3090 a solid place in Local AI.

这条是引用着另一条写的：x.com/lottolabs/status/2112933213194891674